© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    North and South sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    项è§Ħå®ļ
    -0.08
    项
    -0.07
    å¿Į
    -0.07
    bir
    -0.07
     item
    -0.07
    å¿Į讳
    -0.07
    æł¹æį®ä¸įåIJĮçļĦ
    -0.07
    rlen
    -0.06
    .item
    -0.06
    edList
    -0.06
    POSITIVE LOGITS
    ÑħÑĸд
    0.08
    ä¸īåĮº
    0.08
    ModuleName
    0.07
     blocks
    0.07
    çļĦä¸Ģç»Ħ
    0.07
    _MODULES
    0.07
    outh
    0.07
    okies
    0.07
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    0.07
     north
    0.07
    Activations Density 0.005%

    No Known Activations